Refereed full papers (journals, book chapters, international conferences)

1994

@article{SpR1994,
	vgclass =	{refpap},
	vgproject =	{nn,invariance},
	author =	{Lilly Spirkovska and Max B. Reid},
	title =	{Higher-Order Neural Networks Applied to 2{D} and 3{D}
	Object Recognition},
	journal =	{Machine Learning},
	volume =	{15},
	number =	{2},
	pages =	{169--199},
	year =	{1994},
	abstract =	{A higher-order neural network (HONN) can be designed to be
	invariant to geometric transformations such as scale, translation, and
	in-plane rotation. Invariances are built directly into the architecture
	of a HONN and do not need to be learned. Thus, for 2D object
	recognition, the network needs to be trained on just one view of each
	object class, not numerous scaled, translated, and rotated views.
	Because the 2D object recognition task is a component of the 3D object
	recognition task, built-in 2D invariance also decreases the size of the
	training set required for 3D object recognition. We present results for
	2D object recognition both in simulation and within a robotic vision
	experiment and for 3D object recognition in simulation. We also compare
	our method to other approaches and show that HONNs have distinct
	advantages for position, scale, and rotation-invariant object
	recognition.},
}